Active SLAM-based algorithm for autonomous exploration with mobile robot

Trivun, Darko; Salaka, Edin; Osmanković, Dinko; Velagić, Jasmin; Osmić, Nedim

doi:10.1109/icit.2015.7125079

Cited by 22 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…wheel velocities) in order to navigate unknown environments and jointly build the map of the environments. When the SLAM algorithm is used in real-time for actively planning robot paths while simultaneously building the environment map, the SLAM algorithm is named as Active SLAM (Trivun et al, 2015). The most widely used Active SLAM method so far is called frontier-based exploration (Yamauchi, 1997) which generates the control signals simply looking at whether the selected frontier (i.e.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning Helps Slam: Learning to Build Maps

Botteghi

Sırmaçek²,

Schulte

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. In this research, we investigate the use of Reinforcement Learning (RL) for an effective and robust solution for exploring unknown and indoor environments and reconstructing their maps. We benefit from a Simultaneous Localization and Mapping (SLAM) algorithm for real-time robot localization and mapping. Three different reward functions are compared and tested in different environments with growing complexity. The performances of the three different RL-based path planners are assessed not only on the training environments, but also on an a priori unseen environment to test the generalization properties of the policies. The results indicate that RL-based planners trained to maximize the coverage of the map are able to consistently explore and construct the maps of different indoor environments.

show abstract

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning Helps Slam: Learning to Build Maps

Botteghi

Sırmaçek²,

Schulte

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Reference [29] is aimed at solving active SLAM problems where coverage is required and certain constraints are imposed. With that end in view, reference [29] proposes a solution to it that focuses on minimization and area coverage within an MPC (Model Predictive Control) framework. It uses a sub-map joining method to improve both effectiveness and efficiency.…”

Section: Related Workmentioning

confidence: 99%

“…It uses a sub-map joining method to improve both effectiveness and efficiency. The D-opt MPC problem is resolved with recourse to a graph topology and convex optimization and the SQP method is employed to address the coverage problem.The main contribution of [29] is it presents a new method capable of generating a sound collision-free trajectory so as to better perform coverage tasks than many other systems do.…”

Section: Related Workmentioning

confidence: 99%

VIMO: A Visual-Inertial-Magnetic Navigation System Based on Non-Linear Optimization

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Visual-inertial navigation systems are credited with superiority over both pure visual approaches and filtering ones. In spite of the high precision many state-of-the-art schemes have attained, yaw remains unobservable in those systems all the same. More accurate yaw estimation not only means more accurate attitude calculation but also leads to better position estimation. This paper presents a novel scheme that combines visual and inertial measurements as well as magnetic information for suppressing deviation in yaw. A novel method for initializing visual-inertial-magnetic odometers, which recovers the directions of magnetic north and gravity, the visual scalar factor, inertial measurement unit (IMU) biases etc., has been conceived, implemented, and validated. Based on non-linear optimization, a magnetometer cost function is incorporated into the overall optimization objective function as a yawing constraint among others. We have done extensive research and collected several datasets recorded in large-scale outdoor environments to certify the proposed system’s viability, robustness, and performance. Cogent experiments and quantitative comparisons corroborate the merits of the proposed scheme and the desired effect of the involvement of magnetic information on the overall performance.

show abstract

“…where Fo represents the created map feature; x Fo represents the th state vector with created feature. The meaning of formula (6) is that if the th measurement data is from created feature, then joint estimation of vehicle pose and the created feature is carried out. If not, the vehicle pose is estimated only and the th measurement data is saved to create a new map feature.…”

Section: Posterior Probability Distribution Decomposition Strategymentioning

confidence: 99%

“…Compared with EKF-SLAM, FastSLAM has a lower complexity and is more robust regarding the data association problem. Nevertheless, the FastSLAM based on RBPF also suffers from some drawbacks such as particle degeneration, Jacobian Matrix solving and linear processing of nonlinear function [4][5][6]. To deal with these problems, the SLAM based on square root unscented Kalman filter (SRUKF) is proposed.…”

Section: Introductionmentioning

confidence: 99%

A FastSLAM Algorithm Based on Nonlinear Adaptive Square Root Unscented Kalman Filter

Zhang

Zhou

Zhang

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

For fast simultaneous localization and mapping (FastSLAM) problem, to solve the problems of particle degradation, the error introduced by linearization and inconsistency of traditional algorithm, an improved algorithm is described in the paper. In order to improve the accuracy and reliability of algorithm which is applied in the system with lower measurement frequency, a new decomposition strategy is adopted for a posteriori estimation. In proposed decomposition strategy, the problem of solving a 3dimensional state vector and N 2-dimensional state vectors in traditional FastSLAM algorithm is transformed to the problem of solving N 5-dimensional state vectors. Furthermore, a nonlinear adaptive square root unscented Kalman filter (NASRUKF) is used to replace the particle filter and Kalman filter employed by traditional algorithm to reduce the model linearization error and avoid solving Jacobian matrices. Finally, the proposed algorithm is experimentally verified by vehicle in indoor environment. The results prove that the positioning accuracy of proposed FastSLAM algorithm is less than 1 cm and the azimuth angle error is 0.5 degrees.

show abstract

Active SLAM-based algorithm for autonomous exploration with mobile robot

Cited by 22 publications

References 20 publications

Reinforcement Learning Helps Slam: Learning to Build Maps

Reinforcement Learning Helps Slam: Learning to Build Maps

VIMO: A Visual-Inertial-Magnetic Navigation System Based on Non-Linear Optimization

A FastSLAM Algorithm Based on Nonlinear Adaptive Square Root Unscented Kalman Filter

Contact Info

Product

Resources

About